python抓取东方财富网股票的公告的里面的链接

正则表达式匹配网址http://data.eastmoney.com/notice/的公告标题和里面的链接，并自动记录到本地文本里

# -*- coding: UTF-8 -*-
__author__ = 'Intgrp'

import urllib  # 网页操作模块，获取网页数据
import re  # 正则表达式

def get_content_link_title(url):
    html = urllib.urlopen(url).read()
    #匹配出股票的 [链接,公告]
    reg = r'<a\shref=\"(/notice/[0-9]{8}/[^"]+)\"[^>]*>([^<]+)<\/a>'
    reg = re.compile(reg)
    content = re.findall(reg, html)
    return content

def get_content_num(url):
    html = urllib.urlopen(url).read()
    #<a href="/Notice/Noticelist.aspx?type=0&market=all&date=&page=30010" target="_self" hidefocus="true" title="转到最后一页">30010</a>
    #reg = r'<a.*? title="(.*?)">(\d+)</a>'  匹配类似  <a title="  ">数字</a>的类型
    # \xd7\xaa\xb5\xbd\xd7\xee\xba\xf3\xd2\xbb\xd2\xb3  汉子为转到最后一页
    reg = r'<a.*? title="\xd7\xaa\xb5\xbd\xd7\xee\xba\xf3\xd2\xbb\xd2\xb3">(\d+)</a>'
    reg = re.compile(reg)
    page = re.findall(reg,html)
    return page

def get_next_page_link(i):
    #由网页源代码可以得出，链接类型为
    #例如http://data.eastmoney.com/Notice/Noticelist.aspx?type=0&market=all&date=&page=5
    #固得出http://data.eastmoney.com/Notice/Noticelist.aspx?type=0&market=all&date=&page=页码
    return "http://data.eastmoney.com/Notice/Noticelist.aspx?type=0&market=all&date=&page=%s"%i
'''
def content_Write2Txt(filename,content,i):
    f = open(filename,'a')
    f.writelines("----------page_num=%s----------------\n"%i)
    for i in content:
        f.writelines(i[0])
        f.writelines("\t")
        f.writelines(i[1])
        f.write("\n")
    f.close()
'''
def content_Write2Txt(content,i):
    f.writelines("----------page_num=%s----------------\n"%i) #可以去掉
    for i in content:
        f.writelines(i[0])
        f.writelines("\t")
        f.writelines(i[1])
        f.write("\n")


if __name__=="__main__":
    page_num = get_content_num("http://data.eastmoney.com/notice/")#获得总共几页
    print "总共%s页"%page_num[0]

    f = open("test.txt",'a')

    for i in range(1,int(page_num[0])):
        url = get_next_page_link(i)#获取第i页url
        content=get_content_link_title(url)#得出每页的内容
        content_Write2Txt(content,i)#附加形式写入txt文件
        print "第%s页已经完成"%i

    f.close()

    print "write success!"